Your browser doesn't support javascript.
loading
Application of hierarchical clustering to multi-parametric MR in prostate: Differentiation of tumor and normal tissue with high accuracy.
Akamine, Yuta; Ueda, Yu; Ueno, Yoshiko; Sofue, Keitaro; Murakami, Takamichi; Yoneyama, Masami; Obara, Makoto; Van Cauteren, Marc.
Afiliação
  • Akamine Y; Philips Japan, Konan 2-13-37, Minato-ku, Tokyo 108-8507, Japan. Electronic address: yuta.akamine@philips.com.
  • Ueda Y; Philips Japan, Konan 2-13-37, Minato-ku, Tokyo 108-8507, Japan.
  • Ueno Y; Department of Radiology, Kobe University Graduate School of Medicine, 7-5-2 Kusunoki-cho, Chuo-ku, Kobe City, Hyogo 650-0017, Japan.
  • Sofue K; Department of Radiology, Kobe University Graduate School of Medicine, 7-5-2 Kusunoki-cho, Chuo-ku, Kobe City, Hyogo 650-0017, Japan.
  • Murakami T; Department of Radiology, Kobe University Graduate School of Medicine, 7-5-2 Kusunoki-cho, Chuo-ku, Kobe City, Hyogo 650-0017, Japan.
  • Yoneyama M; Philips Japan, Konan 2-13-37, Minato-ku, Tokyo 108-8507, Japan.
  • Obara M; Philips Japan, Konan 2-13-37, Minato-ku, Tokyo 108-8507, Japan.
  • Van Cauteren M; Philips Healthcare BIU MR, Asia Pacific, Konan 2-13-37, Minato-ku, Tokyo 108-8507, Japan.
Magn Reson Imaging ; 74: 90-95, 2020 12.
Article em En | MEDLINE | ID: mdl-32926991
PURPOSE: Hierarchical clustering (HC), an unsupervised machine learning (ML) technique, was applied to multi-parametric MR (mp-MR) for prostate cancer (PCa). The aim of this study is to demonstrate HC can diagnose PCa in a straightforward interpretable way, in contrast to deep learning (DL) techniques. METHODS: HC was constructed using mp-MR including intravoxel incoherent motion, diffusion kurtosis imaging, and dynamic contrast-enhanced MRI from 40 tumor and normal tissues in peripheral zone (PZ) and 23 tumor and normal tissues in transition zone (TZ). HC model was optimized by assessing the combinations of several dissimilarity and linkage methods. Goodness of HC model was validated by internal methods. RESULTS: Accuracy for differentiating tumor and normal tissue by optimal HC model was 96.3% in PZ and 97.8% in TZ, comparable to current clinical standards. Relationship between input (DWI and permeability parameters) and output (tumor and normal tissue cluster) was shown by heat maps, consistent with literature. CONCLUSION: HC can accurately differentiate PCa and normal tissue, comparable to state-of-the-art diffusion based parameters. Contrary to DL techniques, HC is an operator-independent ML technique producing results that can be interpreted such that the results can be knowledgeably judged.
Assuntos
Palavras-chave

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Próstata / Neoplasias da Próstata / Processamento de Imagem Assistida por Computador / Imageamento por Ressonância Magnética / Aprendizado de Máquina não Supervisionado Tipo de estudo: Diagnostic_studies / Guideline Limite: Aged / Humans / Male / Middle aged Idioma: En Ano de publicação: 2020 Tipo de documento: Article

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Próstata / Neoplasias da Próstata / Processamento de Imagem Assistida por Computador / Imageamento por Ressonância Magnética / Aprendizado de Máquina não Supervisionado Tipo de estudo: Diagnostic_studies / Guideline Limite: Aged / Humans / Male / Middle aged Idioma: En Ano de publicação: 2020 Tipo de documento: Article